link: https://pan.baidu.com/s/1UkMwdntwAc5paCWHoZHj9w 
  password：9m3z

docker image load < fosun_aitrox.tgz
nvidia-docker container run --name fosun_aitrox --rm -v $PWD/inputs/:/workspace/inputs/ -v $PWD/outputs/:/workspace/outputs/ fosun_aitrox:latest /bin/bash -c "sh predict.sh"'

Installation step by step

Environment

• Ubuntu 16.04.12
• Python 3.6+
• Pytorch 1.5.0+
• CUDA 10.0+

1.Git clone

git clone https://github.com/Shanghai-Aitrox-Technology/EfficientSegmentation.git

2.Install Nvidia Apex

• Perform the following command:

git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --no-cache-dir ./

3.Install dependencies

pip install -r requirements.txt

Get Started

preprocessing

1. Download FLARE21, resulting in 361 training images and masks, 50 validation images.
2. Copy image and mask to ‘FlareSeg/dataset/’ folder.
3. Edit the ‘FlareSeg/data_prepare/config.yaml’. ‘DATA_BASE_DIR'(Default: FlareSeg/dataset/) is the base dir of databases. If set the ‘IS_SPLIT_5FOLD'(Default: False) to true, 5-fold cross-validation datasets will be generated.
4. Run the data preprocess with the following command:

python FlareSeg/data_prepare/run.py

The image data and lmdb file are stored in the following structure:

DATA_BASE_DIR directory structure：
├── train_images
   ├── train_000_0000.nii.gz
   ├── train_001_0000.nii.gz
   ├── train_002_0000.nii.gz
   ├── ...
├── train_mask
   ├── train_000.nii.gz
   ├── train_001.nii.gz
   ├── train_002.nii.gz
   ├── ...
└── val_images
    ├── validation_001_0000.nii.gz
    ├── validation_002_0000.nii.gz
    ├── validation_003_0000.nii.gz
    ├── ...
├── file_list
    ├──'train_series_uids.txt', 
    ├──'val_series_uids.txt',
    ├──'lesion_case.txt',
├── db
    ├──seg_raw_train         # The 361 training data information.
    ├──seg_raw_test          # The 50 validation images information.
    ├──seg_train_database    # The default training database.
    ├──seg_val_database      # The default validation database.
    ├──seg_pre-process_database # Temporary database.
    ├──seg_train_fold_1
    ├──seg_val_fold_1
├── coarse_image
    ├──160_160_160
          ├── train_000.npy
          ├── train_001.npy
          ├── ...
├── coarse_mask
    ├──160_160_160
          ├── train_000.npy
          ├── train_001.npy
          ├── ...
├── fine_image
    ├──192_192_192
          ├── train_000.npy
          ├── train_001.npy
          ├──  ...
├── fine_mask
    ├──192_192_192
          ├── train_000.npy
          ├── train_001.npy
          ├── ...

The data information is stored in the lmdb file with the following format:

{
    series_id = {
        'image_path': data.image_path,
        'mask_path': data.mask_path,
        'smooth_mask_path': data.smooth_mask_path,
        'coarse_image_path': data.coarse_image_path,
        'coarse_mask_path': data.coarse_mask_path,
        'fine_image_path': data.fine_image_path,
        'fine_mask_path': data.fine_mask_path
    }
}

Training

Remark: Coarse segmentation is trained on Nvidia GeForce 2080Ti(Number:8) in the experiment, while fine segmentation on Nvidia A100(Number:4). If you use different hardware, please set the “ENVIRONMENT.NUM_GPU”, “DATA_LOADER.NUM_WORKER” and “DATA_LOADER.BATCH_SIZE” in ‘FlareSeg/coarse_base_seg/config.yaml’ and ‘FlareSeg/fine_efficient_seg/config.yaml’ files.

Coarse segmentation:

• Edit the ‘FlareSeg/coarse_base_seg/config.yaml’
• Train coarse segmentation with the following command:

cd FlareSeg/coarse_base_seg
sh run.sh

Fine segmentation:

• Edit the ‘FlareSeg/fine_efficient_seg/config.yaml’.
• Edit the ‘FlareSeg/fine_efficient_seg/run.py’, set the ‘tune_params’ for different experiments.
• Train fine segmentation with the following command:

cd  FlareSeg/fine_efficient_seg
sh run.sh

Inference:

• The model weights are stored in ‘FlareSeg/model_weights/’.
• Run the inference with the following command:

sh predict.sh

Contact

This repository is currently maintained by Fan Zhang ([email protected]) and Yu Wang ([email protected])

Citation

Acknowledgement

GitHub

GitHub - Shanghai-Aitrox-Technology/EfficientSegmentation: Segmentation for medical image.

Segmentation for medical image. Contribute to Shanghai-Aitrox-Technology/EfficientSegmentation development by creating an account on GitHub.

GitHubShanghai-Aitrox-Technology